fast-filesystem-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CREATE_BACKUP_FILES | No | Control backup file creation behavior. When set to 'true', creates backup files before modifications. When set to 'false' (default), disables backup file creation to reduce clutter. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fast_list_allowed_directoriesB | Lists the allowed directories |
| fast_read_fileB | Reads a file (with auto-chunking support) |
| fast_read_multiple_filesB | Reads the content of multiple files simultaneously (supports sequential reading) |
| fast_write_fileC | Writes or modifies a file (provides emoji guidelines) |
| fast_large_write_fileA | Reliably writes large files (with streaming, retry, backup, and verification features) |
| fast_list_directoryB | Lists the contents of a directory (with auto-chunking and pagination support) |
| fast_get_file_infoB | Gets detailed information about a file or directory |
| fast_create_directoryC | Creates a directory |
| fast_search_filesB | Searches for files (by name/content) - supports auto-chunking, regex, context, and line numbers |
| fast_search_codeB | Searches for code (ripgrep-style) - provides auto-chunking, line numbers, and context |
| fast_get_directory_treeC | Gets the directory tree structure |
| fast_get_disk_usageC | Gets disk usage information |
| fast_find_large_filesC | Finds large files |
| fast_edit_blockC | Precise block editing: safely replace exact matches (desktop-commander style) |
| fast_safe_editB | Safe smart editing: Detects risks and provides interactive confirmation |
| fast_edit_multiple_blocksC | Edits multiple parts of a file at once |
| fast_edit_blocksC | Processes multiple precise block edits at once (array of fast_edit_block) |
| fast_extract_linesD | Extracts specific lines from a file |
| fast_copy_fileC | Copies a file or directory |
| fast_move_fileB | Moves or renames a file or directory |
| fast_delete_fileC | Deletes a file or directory |
| fast_batch_file_operationsC | Performs batch operations on multiple files |
| fast_compress_filesC | Compresses files or directories |
| fast_extract_archiveC | Extracts an archive file |
| fast_sync_directoriesC | Synchronizes two directories |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 25 tools
Most tools are distinct, but there is notable overlap between fast_edit_block, fast_safe_edit, fast_edit_multiple_blocks, and fast_edit_blocks—all handle editing and could confuse an agent. Similarly, fast_search_files and fast_search_code have overlapping purposes despite different descriptions.
The fast_ prefix is applied consistently and most tools follow a verb_noun pattern (e.g., fast_read_file, fast_create_directory). Minor deviations like fast_edit_blocks vs fast_edit_multiple_blocks and fast_batch_file_operations are slightly inconsistent but still readable.
25 tools is at the upper boundary of what is reasonable for a filesystem server. The count feels heavy because several tools overlap (multiple edit variants, two search tools, multiple read/write variants), but each has a plausible use case.
The tool surface covers the full filesystem lifecycle: read, write, edit, list, search, create, copy, move, delete, batch operations, compression, sync, and disk usage. There are no obvious dead ends for common file operations.